Commit Graph

276 Commits

Author SHA1 Message Date
Matt Arsenault
94437c9691 Use right address space pointer size
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194940 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-17 00:06:39 +00:00
Matt Arsenault
e6e811277f Fix assert on unaligned access to global with different address space size.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194934 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-16 20:50:54 +00:00
Matt Arsenault
4fe5b640ee Fix codegen for null different sized pointer.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194932 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-16 20:24:41 +00:00
Vincent Lejeune
4110797853 R600: Make dot_4 instructions predicable
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194927 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-16 16:24:41 +00:00
Tom Stellard
5cddda6d13 R600/SI: Add VReg_96 register class to SIRegisterInfo::hasVGPRs()
This fixes a crash with GNOME settings manager.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194836 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-15 18:26:45 +00:00
Matt Arsenault
509a492442 Add target hook to prevent folding some bitcasted loads.
This is to avoid this transformation in some cases:
fold (conv (load x)) -> (load (conv*)x)

On architectures that don't natively support some vector
loads efficiently casting the load to a smaller vector of
larger types and loading is more efficient.

Patch by Micah Villmow.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194783 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-15 04:42:23 +00:00
Tom Stellard
19a99df130 R600: Fix scheduling of instructions that use the LDS output queue
The LDS output queue is accessed via the OQAP register.  The OQAP
register cannot be live across clauses, so if value is written to the
output queue, it must be retrieved before the end of the clause.
With the machine scheduler, we cannot statisfy this constraint, because
it lacks proper alias analysis and it will mark some LDS accesses as
having a chain dependency on vertex fetches.  Since vertex fetches
require a new clauses, the dependency may end up spiltting OQAP uses and
defs so the end up in different clauses.  See the lds-output-queue.ll
test for a more detailed explanation.

To work around this issue, we now combine the LDS read and the OQAP
copy into one instruction and expand it after register allocation.

This patch also adds some checks to the EmitClauseMarker pass, so that
it doesn't end a clause with a value still in the output queue and
removes AR.X and OQAP handling from the scheduler (AR.X uses and defs
were already being expanded post-RA, so the scheduler will never see
them).

Reviewed-by: Vincent Lejeune <vljn at ovi.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194755 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-15 00:12:45 +00:00
Matt Arsenault
e0375295c5 R600/SI: Add testcase for problem I ran into
with the older version of the moveToVALU changes.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194682 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-14 07:57:29 +00:00
Tom Stellard
a2b4eb6d15 R600/SI: Add support for private address space load/store
Private address space is emulated using the register file with
MOVRELS and MOVRELD instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194626 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-13 23:36:50 +00:00
Tom Stellard
b52bf6a3b3 R600/SI: Prefer SALU instructions for bit shift operations
All shift operations will be selected as SALU instructions and then
if necessary lowered to VALU instructions in the SIFixSGPRCopies pass.

This allows us to do more operations on the SALU which will improve
performance and is also required for implementing private memory
using indirect addressing, since the private memory pointers must stay
in the scalar registers.

This patch includes some fixes from Matt Arsenault.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194625 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-13 23:36:37 +00:00
Matt Arsenault
29f1788de9 R600: Fix selection failure on EXTLOAD
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194547 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-13 02:39:07 +00:00
Matt Arsenault
86245071b5 R600/SI: Change formatting of printed registers.
Print the range of registers used with a single letter prefix.
This better matches what the shader compiler produces and
is overall less obnoxious than concatenating all of the
subregister names together.

Instead of SGPR0, it will print s0. Instead of SGPR0_SGPR1,
it will print s[0:1] and so on.

There doesn't appear to be a straightforward way
to get the actual register info in the InstPrinter,
so this parses the generated name to print with the
new syntax.

The required test changes are pretty nasty, and register
matching regexes are now worse. Since there isn't a way to
add to a variable in FileCheck, some of the tests now don't
check the exact number of registers used, but I don't think that
will be a real problem.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194443 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-12 02:35:51 +00:00
Matt Arsenault
e57a8a3d10 R600/SI: Add test that fails due to requiring i64 mul for pointers
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194433 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-11 23:31:02 +00:00
Vincent Lejeune
70a7d5ddb4 R600: Use function inputs to represent data stored in gpr
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194425 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-11 22:10:24 +00:00
Vincent Lejeune
69239a98b6 R600: Fix LowerUDIVREM
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@194153 91177308-0d34-0410-b5e6-96231b3b80d8
2013-11-06 17:36:04 +00:00
Matt Arsenault
4f17f88071 Fix CodeGen for unaligned loads with address spaces
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193721 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-30 23:30:05 +00:00
Tom Stellard
aa1d078e7f R600: Custom lower f32 = uint_to_fp i64
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193701 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-30 17:22:05 +00:00
Tom Stellard
54328c772c R600/SI: Add compute support for CI v2
v2:
  - Fix LDS size calculation

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193621 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-29 16:37:28 +00:00
Tom Stellard
f54a8409f9 R600: Expand vector FSQRT ops
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193620 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-29 16:37:20 +00:00
Tom Stellard
96b5670cf4 R600/SI: fix MIMG writemask adjustement
This fixes piglit:
- shaders/glsl-fs-texture2d-masked
- shaders/glsl-fs-texture2d-masked-4

Patch by: Marek Olšák

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193222 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-23 02:53:47 +00:00
Tom Stellard
f95b162188 R600: Fix handling of vector kernel arguments
The SelectionDAGBuilder was promoting vector kernel arguments to legal
types, but this won't work for R600 and SI since kernel arguments are
stored in memory and can't be promoted.  In order to handle vector
arguments correctly we need to look at the original types from the LLVM IR
function.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193215 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-23 00:44:32 +00:00
Tom Stellard
6a2f9b9137 R600/SI: Add support for i64 bitwise or
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193213 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-23 00:44:19 +00:00
Tom Stellard
f9e5c39811 R600/SI: Use S_LOAD_DWORD instructions for v8i32 and v16i32
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193212 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-23 00:44:12 +00:00
Tom Stellard
04c559569f R600: Simplify handling of private address space
The AMDGPUIndirectAddressing pass was previously responsible for
lowering private loads and stores to indirect addressing instructions.
However, this pass was buggy and way too complicated.  The only
advantage it had over the new simplified code was that it saved one
instruction per direct write to private memory.  This optimization
likely has a minimal impact on performance, and we may be able
to duplicate it using some other transformation.

For the private address space, we now:
1. Lower private loads/store to Register(Load|Store) instructions
2. Reserve part of the register file as 'private memory'
3. After regalloc lower the Register(Load|Store) instructions to
   MOV instructions that use indirect addressing.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193179 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-22 18:19:10 +00:00
Matt Arsenault
2d7d477d94 Fix CodeGen for vectors of pointers with address spaces.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193112 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-21 20:03:58 +00:00
Matt Arsenault
ff71812dfa Fix CodeGen for different size address space GEPs
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@193111 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-21 20:03:54 +00:00
Tom Stellard
a4f468f245 R600: Fix a crash in the AMDILCFGStructurizer
We were calling llvm_unreachable() when failing to optimize the
branch into if case.  However, it is still possible for us
to structurize the CFG by duplicating blocks even if this optimization
fails.

Reviewed-by: Vincent Lejeune<vljn at ovi.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192813 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-16 17:06:02 +00:00
Vincent Lejeune
cf1f4c7dd1 R600: improve dump of S_WAITCNT
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192557 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-13 17:56:28 +00:00
Vincent Lejeune
f2b3a569ae R600: Use masked read sel for texture instructions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192554 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-13 17:56:10 +00:00
Vincent Lejeune
91ec4b0cac R600: fix swizzle export
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192553 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-13 17:56:04 +00:00
Matt Arsenault
b19b474de9 R600: Add scalar i32 add test
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192501 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-11 21:03:41 +00:00
Matt Arsenault
2ad612a9e7 Use CHECK-LABEL
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192500 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-11 21:03:39 +00:00
Matt Arsenault
1cc41bf63c R600: Fix trunc i64 to i32 on SI
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192375 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-10 18:04:16 +00:00
Tom Stellard
3986785046 R600/SI: Use -verify-machineinstrs for most tests
We can't enable the verifier for tests with SI_IF and SI_ELSE, because
these instructions are always followed by a COPY which copies their
result to the next basic block.  This violates the machine verifier's
rule that non-terminators can not folow terminators.

Reviewed-by: Vincent Lejeune<vljn at ovi.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192366 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-10 17:11:46 +00:00
Matt Arsenault
194d437f11 Add some xfaild R600 tests.
These are bugs to fix later.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@192212 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-08 18:06:36 +00:00
Vincent Lejeune
dfef7cbfc6 R600: add a pass that merges clauses.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191790 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-01 19:32:58 +00:00
Vincent Lejeune
c6c37d74a2 R600: Put PRED_X instruction in its own clause
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191789 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-01 19:32:49 +00:00
Vincent Lejeune
5b00e833fa R600: Enable -verify-machineinstrs in some tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191788 91177308-0d34-0410-b5e6-96231b3b80d8
2013-10-01 19:32:38 +00:00
Manman Ren
e267f04ef5 TBAA: update tbaa format from scalar format to struct-path aware format.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191690 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-30 18:17:55 +00:00
Manman Ren
aef1b37824 TBAA: remove !tbaa from testing cases when they are not needed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191689 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-30 18:17:35 +00:00
Tom Stellard
9c598cfebc R600: Fix handling of NAN in comparison instructions
We were completely ignoring the unorder/ordered attributes of condition
codes and also incorrectly lowering seto and setuo.

Reviewed-by: Vincent Lejeune<vljn at ovi.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@191603 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-28 02:50:50 +00:00
Vincent Lejeune
f57d692c11 R600: Move code handling literal folding into R600ISelLowering.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190644 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-12 23:44:53 +00:00
Vincent Lejeune
fe78318614 R600: Move fabs/fneg/sel folding logic into PostProcessIsel
This move makes possible to correctly handle multiples instructions
from a single pattern.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190643 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-12 23:44:44 +00:00
Tom Stellard
a3c2bcf0ee R600/SI: expose TBUFFER_STORE_FORMAT_* for OpenGL transform feedback
For _XYZ, the type of VDATA is v4i32, because v3i32 doesn't exist.

The ADDR64 bit is not exposed. A simpler intrinsic that doesn't take
a resource descriptor might be nicer.

The maximum number of input SGPRs is bumped to 17.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190575 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-12 02:55:14 +00:00
Aaron Watry
546dcc5ddc R600: Add support for LDS atomic subtract
Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190200 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-06 20:17:42 +00:00
Matt Arsenault
ce8e4647bf Teach CodeGenPrepare about address spaces
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190112 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-06 00:18:43 +00:00
Matt Arsenault
3987e532f7 R600: Fix i64 to i32 trunc on SI
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190091 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 19:41:10 +00:00
Tom Stellard
79916948e1 R600: Add support for local memory atomic add
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190080 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 18:38:09 +00:00
Tom Stellard
756f382ac1 R600: Expand SELECT nodes rather than custom lowering them
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190079 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 18:38:03 +00:00
Tom Stellard
470c451574 R600: Fix incorrect LDS size calculation
GlobalAdderss nodes that appeared in more than one basic block were
being counted twice.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190078 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-05 18:37:57 +00:00